← Back to community benchmarks
Qwen3.5-27B
Performance
8k
tokens
97.2
PP tok/s
8.0
TG tok/s
84262
TTFT (ms)
17.4
Peak mem (GB)
Hardware
Chip
M3 Pro (18c)
Memory
36 GB
GPU Cores
18
Software
oMLX
v0.2.6
macOS
macOS 26.3
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 97.4 | 8.6 | 16.6 GB | view |
| 4k | 98.0 | 8.1 | 17.0 GB | view |
| 8k | 97.2 | 8.0 | 17.4 GB | current |
| 16k | 94.3 | 7.3 | 18.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 8.6 | 1.00× |
| 2× | 17.0 | 1.98× |
| 4× | 25.5 | 2.97× |
| 8× | 25.8 | 3.00× |